12 papers
Counterfactual Transition Graphs: Evaluating Cross-Class Transition Quality
Syed Muhammad Hamza Zaidi, Szymon Bobek, Grzegorz J. Nalepa +1
Counterfactual (CF) explanations for time-series classifiers are usually evaluated one example at a time: what minimal edit flips this single window's prediction? We argue that the…
Actionable and diverse counterfactual explanations incorporating domain knowledge and plausibility constraints
Szymon Bobek, Åukasz BaÅec, Grzegorz J. Nalepa
Counterfactual explanations improve the actionable interpretability of machine learning models by identifying minimal changes required to achieve a desired outcome. However, existi…
Validating the Clinical Utility of CineECG 3D Reconstructions through Cross-Modal Feature Attribution
Karol Dobiczek, Maciej Mozolewski, Szymon Bobek +3
Deep learning models for 12-lead electrocardiogram (ECG) analysis achieve high diagnostic performance but lack the intuitive interpretability required for clinical integration. Sta…
Towards Differentiating Between Failures and Domain Shifts in Industrial Data Streams
Natalia Wojak-Strzelecka, Szymon Bobek, Grzegorz J. Nalepa +1
Anomaly and failure detection methods are crucial in identifying deviations from normal system operational conditions, which allows for actions to be taken in advance, usually prev…
From Prototypes to Sparse ECG Explanations: SHAP-Driven Counterfactuals for Multivariate Time-Series Multi-class Classification
Maciej Mozolewski, Betül Bayrak, Kerstin Bach +1
In eXplainable Artificial Intelligence (XAI), instance-based explanations for time series have gained increasing attention due to their potential for actionable and interpretable i…
Explaining Time Series Classifiers with PHAR: Rule Extraction and Fusion from Post-hoc Attributions
Maciej Mozolewski, Szymon Bobek, Grzegorz J. Nalepa
Explaining machine learning (ML) models for time series (TS) classification remains challenging due to the difficulty of interpreting raw time series and the high dimensionality of…